Uriel Cholula, Manuel A. Andrade, Juan K.Q. Solomon
Increasing water demands and prolonged droughts are forcing many farmers in Nevada to grow alfalfa (Medicago sativa L.) under deficit irrigation (DI). While DI can increase crop water productivity (CWP), it can also lead to water stress conditions that reduce yield. This study assessed the effects of DI on yield, nutritive value, and CWP of two alfalfa varieties marketed as drought-tolerant (Ladak II) and highly productive (Stratica). An experiment was conducted at the Valley Road Field Lab in Reno, Nevada, over three growing seasons (2021–2023), in which the following three irrigation treatments were applied to both varieties: 100 % (full irrigation, FI), 80 % (mild DI), and 60 % (moderate DI) of replenishment of soil water depletion to field capacity. Irrigation amounts applied to each treatment were delivered by a surface drip irrigation system and calculated from volumetric water content measurements collected by soil moisture sensors based on time-domain reflectometry. Seasonal water use of each alfalfa variety and treatment was estimated using a soil water balance. Over the years, moderate DI decreased seasonal dry yield by 13.9 % and mild DI by 4.6 % compared to FI. The drought-tolerant variety produced similar yields to the highly productive variety when both received the same irrigation treatment. Irrigation treatment significantly affected (p < 0.01) the seasonal mean CWP across years, which improved under DI. Seasonal mean CWP increased from 11.5 kg ha−1 mm−1 in the 2021 season to 19.2 and 18.5 kg ha−1 mm−1 in 2022 and 2023, respectively. Across seasons, mean acid detergent fiber (ADF) was not affected by irrigation treatment, but neutral detergent fiber (NDF) (p < 0.001) and relative feed value (RFV) (p < 0.01) were significantly influenced by irrigation treatment. Forage nutritive value was not affected by alfalfa variety. These findings suggest that while DI could reduce alfalfa yield, it enhances CWP and can improve nutritive value, being a viable strategy under water-limited conditions. In northern Nevada’s semiarid conditions, a mild DI appears to be the best option for producers because it offers a balance between alfalfa yield, nutritive value, and potential water savings.
Blessing Nnenna Azubuike, Anna Chlingaryan, Martin Correa-Luna
et al.
With feed costs accounting for about 40-60 % of milk production expenses in Australia, efficient supplementary concentrate allocation is crucial for profitability. Despite an increase in concentrate use per cow over the past decade, the average milk yield response remains about 1 L per kg of dry matter concentrate. While machine learning and data-driven optimisation are widely utilised in sectors such as engineering, healthcare, and finance, their application in feed optimisation within dairy farming has not been extensively researched. This study aims to develop a machine learning-based method to optimise individual cow supplement allocation, using similar total daily concentrate with a tolerance range allowing for a 2-10 % decrease, to maximise milk yield. Data from a controlled field study involving 130 lactating Holstein-Friesians (32,504 records) were analysed.Sixteen machine learning algorithms were evaluated to predict milk yield based on concentrate allocation and available cattle data (days in milk, daily milk yield and liveweight, and parity number). The Random Forest (RF) model was the best performer, achieving an R² of 0.60 and RMSE of 4.20 L/cow/day. Then 7371 records from 81 cows over 91 days were employed to run the concentrate levels optimisation using the Dirichlet-Rescale (DRS) algorithm and Monte Carlo simulation. The RF model and SciPy optimisation determined optimal individual cow allocations (5-9 kg/cow.day-1). Implementing this resulted in a herd-level 8 % increase in daily milk yield. This study highlights the potential benefits of adopting data-driven algorithms for individualised dairy feed optimisation based on observed correlations within existing management practices. While results suggest improvement over conventional flat-rate methods, the study is limited by the nature of the dataset, and findings reflect associations under standard practice rather than experimental manipulation of concentrate levels, requiring validation through controlled field trials to confirm practical efficacy and economic impact in actual dairy farming contexts.
Mohamed Mansour, Kiran Kumar Sathyanarayanan, Philipp Sauerteig
et al.
Climate control in semi-closed greenhouses is essential for maximizing crop yield and ensuring energy-efficient operation. Model Predictive Control (MPC) is widely used to optimize control inputs based on system dynamics and operational constraints. However, standard MPC performance can degrade under various system uncertainties. While robust and stochastic MPC address these challenges, they often entail high computational costs. Moreover, adapting them to new greenhouse configurations typically requires model reparameterization or implementing adaptive MPC, which limits scalability. In contrast, model-free approaches like Deep Reinforcement Learning (DRL) offer inherent adaptability by learning control policies directly from data, making them well-suited for handling uncertainties. However, DRL methods can require extensive training data and may suffer from instability during learning. To address these limitations while leveraging the strengths of both approaches, we propose a hierarchical control framework that integrates MPC and DRL. The framework integrates an upper-level controller, which performs economic optimization by considering dynamic energy pricing, with a low-level DRL-based controller that ensures robust real-time reference tracking. The DRL-based controller is trained using a two-stage strategy to ensure robustness and adaptability. We demonstrate the controller's robustness through simulations of a semi-closed greenhouse under three scenarios, including actuator failures and environmental fluctuations. Furthermore, we demonstrate the controller's adaptability when deployed in a similar but structurally altered greenhouse. Results indicate that the DRL-based controller maintains stable greenhouse conditions under various challenges, and can easily adapt to different greenhouse setups. This highlights its potential as a reliable and scalable solution for climate control in modern greenhouse farming.
IntroductionIran, with a wide variety of climates, is among the top 20 countries in the world in terms of medicinal plant production, yet it does not have a significant position among the top exporting countries of medicinal plants and related products. Therefore, this exploratory descriptive research was conducted with the aim of analyzing the strategic development for sustainable export of medicinal plants from Iran to the global value chain using the SWOT technique.MethodsThe study population consisted of three groups: experts in medicinal plants, managers and relevant experts in agricultural administrations, natural resources and watershed management, Agriculture and natural resources research and education center, as well as producers, traders, and managers in the field of medicinal plants, with 31 individuals selected purposefully as a sample using snowball sampling method.Results and discussionBased on the findings, 10 strengths, 25 weaknesses, 11 opportunities, and 16 threats were identified. The results indicated that the average weaknesses outweighed the strengths, and threats outweighed the opportunities. Therefore, the strategic quadrant of the SWOT matrix was placed on the WT (defensive strategies). Accordingly, some proposed strategies such as “Encouraging regional investment in the field of medicinal plant processing industries” and “Reforming and facilitating administrative bureaucracy to obtain necessary licenses for final product production” were suggested to play a more significant role in the development of medicinal plant production and processing. The findings of this study can be utilized by decision-makers and relevant policymakers in planning and for sustainable development of Iranian medicinal plant exports in the global value chain.
Nutrition. Foods and food supply, Food processing and manufacture
India's growing population and economy have significantly increased the demand and consumption of natural resources. As a result, the potential benefits of transitioning to a circular economic model have been extensively discussed and debated among various Indian stakeholders, including policymakers, industry leaders, and environmental advocates. Despite the numerous initiatives, policies, and transnational strategic partnerships of the Indian government, most small and medium enterprises in India face significant challenges in implementing circular economy practices. This is due to the lack of a clear pathway to measure the current state of the circular economy in Indian industries and the absence of a framework to address these challenges. This paper examines the circularity of the 93-textile industry in India using the C-Readiness Tool. The analysis comprehensively identified 9 categories with 34 barriers to adopting circular economy principles in the textile sector through a narrative literature review. The identified barriers were further compared against the findings from a C-readiness tool assessment, which revealed prominent challenges related to supply chain coordination, consumer engagement, and regulatory compliance within the industry's circularity efforts. In response to these challenges, the article proposes a strategic roadmap that leverages digital technologies to drive the textile industry towards a more sustainable and resilient industrial model.
Simon Hellmann, Terrance Wilms, Stefan Streif
et al.
In many applications of biotechnology, measurements are available at different sampling rates, e.g., due to online sensors and offline lab analysis. Offline measurements typically involve time delays that may be unknown a priori due to the underlying laboratory procedures. This multirate (MR) setting poses a challenge to Kalman filtering, where conventionally measurement data is assumed to be available on an equidistant time grid and without delays. This tutorial paper derives the MR version of an extended Kalman filter (EKF) based on sample state augmentation, and applies it to the anaerobic digestion (AD) process in a simulative agricultural setting. The performance of the MR-EKF is investigated for various scenarios including varying delay lengths, measurement noise levels, plant-model mismatch (PMM), and initial state error. Provided with an adequate tuning, the MR-EKF can reliably estimate the process state and, thus, appropriately fuse the delayed offline measurements and smooth the noisy online measurements. Because of the sample state augmentation approach, the delay length of offline measurements does not critically effect the performance of the state estimation, provided that observability is not lost during the delays. Poor state initialization and PMM affect convergence more than measurement noise levels. Furthermore, selecting an appropriate tuning was found to be critically important for successful application of the MR-EKF for which a systematic approach is presented. This tutorial provides implementation guidance for practitioners seeking to successfully apply state estimation for multirate systems. Thus, it contributes to the development of demand-driven operation of biogas plants, which may aid in stabilizing a renewable electricity grid.
This paper highlights the significance of resource-constrained Internet of Things (RCD-IoT) systems in addressing the challenges faced by industries with limited resources. This paper presents an energy-efficient solution for industries to monitor and control their utilities remotely. Integrating intelligent sensors and IoT technologies, the proposed RCD-IoT system aims to revolutionize industrial monitoring and control processes, enabling efficient utilization of resources.The proposed system utilized the IEEE 802.15.4 WiFi Protocol for seamless data exchange between Sensor Nodes. This seamless exchange of information was analyzed through Packet Tracer. The system was equipped with a prototyped, depicting analytical chemical process to analyze the significant performance metrics. System achieved average Round trip time (RTT) of just 12ms outperforming the already existing solutions presented even with higher Quality of Service (QoS) under the transmission of 1500 packets/seconds under different line of sight (LOS) and Non line of sight (NLOS) fadings.
Troy Bosher, Maria M. Della Rosa, M. Ajmal Khan
et al.
ABSTRACT The current New Zealand greenhouse gas inventory predictions assume that dairy cows consume pasture only, but the use of supplemental feeds, including concentrates, on New Zealand dairy farms has increased greatly in recent decades. The objective of this study was to evaluate the effect of feeding graded levels of concentrates on methane (CH 4 ) emissions in lactating dairy cows within a pastoral system. Early lactation dairy cows ( n = 72) were allocated ( n = 18 per treatment) to receive 0, 2, 4 and 6 kg dry matter (DM) of treatment concentrates per day during milking. The cows grazed pasture ad libitum and CH 4 emissions were measured in the paddocks using automated emissions monitoring systems called ‘GreenFeed’. Gross CH 4 emissions (g/d) were similar for cows across the four dietary treatments, while CH 4 emissions intensity (g/kg fat and protein corrected milk production (FPCM) and milk solids production) linearly decreased with increasing concentrate inclusion in the diet ( P < 0.02). The CH 4 intensity decreased linearly ( r 2 = 0.42) and quadratically ( r 2 = 0.53) with increasing FPCM production.
Image analysis is being developed to improve the efficiency of fishery and aquaculture technologies. Optical cameras are an easy and cost-effective method for monitoring fish and other species. In this study, a monitoring system that combines an underwater time-lapse camera and a deep learning-based image analysis was developed for utilization in integrated multi-trophic aquaculture (IMTA). The sea cucumber (Apostichopus japonicus) was used as a target species because the technology necessary for estimating growth, particularly in terms of weight, of caged sea cucumber using an underwater environment is still under study. Therefore, semantic segmentation was applied to classify the images into caged sea cucumbers and various underwater backgrounds. Multiple images of sea cucumbers were captured in a water tank that mimicked the box cage used in IMTA, and their body weights were measured simultaneously. For model development, approximately 1,300 images were prepared for the training and validation processes. The model then achieved an IoU (Intersection over Union) of approximately 94 % for the validation data. Next, the pixel numbers of sea cucumbers were converted into an area calculated using the size of the cage net as the background. The relationship between the area and weight of sea cucumbers yielded an approximate line for estimating body weight. As a result, the approximation line had a coefficient of determination of R2 = 0.87 for training and validation data and RMSE (Root Mean Square Error) =1.81 and 6.78 g for sea cucumbers less than 10 and 110 g, respectively. Using the model, test images in an actual IMTA situation were applied, and the estimated body weights were close to the measured values for small sea cucumbers. If we apply this model to images obtained over an extended period, the growth of sea cucumbers in a time series can be understood.
The COVID-19 pandemic has had a long-term impact on industries worldwide, with the hospitality and food industry facing significant challenges, leading to the permanent closure of many restaurants and the loss of jobs. In this study, we developed an innovative analytical framework using Hamiltonian Monte Carlo for predictive modeling with Bayesian regression, aiming to estimate the change point in consumer behavior towards different types of restaurants due to COVID-19. Our approach emphasizes a novel method in computational analysis, providing insights into customer behavior changes before and after the pandemic. This research contributes to understanding the effects of COVID-19 on the restaurant industry and is valuable for restaurant owners and policymakers.
In precision agriculture, vision models often struggle with new, unseen fields where crops and weeds have been influenced by external factors, resulting in compositions and appearances that differ from the learned distribution. This paper aims to adapt to specific fields at low cost using Unsupervised Domain Adaptation (UDA). We explore a novel domain shift from a diverse, large pool of internet-sourced data to a small set of data collected by a robot at specific locations, minimizing the need for extensive on-field data collection. Additionally, we introduce a novel module -- the Multi-level Attention-based Adversarial Discriminator (MAAD) -- which can be integrated at the feature extractor level of any detection model. In this study, we incorporate MAAD with CenterNet to simultaneously detect leaf, stem, and vein instances. Our results show significant performance improvements in the unlabeled target domain compared to baseline models, with a 7.5% increase in object detection accuracy and a 5.1% improvement in keypoint detection.
The optimisation of crop harvesting processes for commonly cultivated crops is of great importance in the aim of agricultural industrialisation. Nowadays, the utilisation of machine vision has enabled the automated identification of crops, leading to the enhancement of harvesting efficiency, but challenges still exist. This study presents a new framework that combines two separate architectures of convolutional neural networks (CNNs) in order to simultaneously accomplish the tasks of crop detection and harvesting (robotic manipulation) inside a simulated environment. Crop images in the simulated environment are subjected to random rotations, cropping, brightness, and contrast adjustments to create augmented images for dataset generation. The you only look once algorithmic framework is employed with traditional rectangular bounding boxes for crop localization. The proposed method subsequently utilises the acquired image data via a visual geometry group model in order to reveal the grasping positions for the robotic manipulation.
Mahsa Khosravi, Matthew Carroll, Kai Liang Tan
et al.
Agricultural production requires careful management of inputs such as fungicides, insecticides, and herbicides to ensure a successful crop that is high-yielding, profitable, and of superior seed quality. Current state-of-the-art field crop management relies on coarse-scale crop management strategies, where entire fields are sprayed with pest and disease-controlling chemicals, leading to increased cost and sub-optimal soil and crop management. To overcome these challenges and optimize crop production, we utilize machine learning tools within a virtual field environment to generate localized management plans for farmers to manage biotic threats while maximizing profits. Specifically, we present AgGym, a modular, crop and stress agnostic simulation framework to model the spread of biotic stresses in a field and estimate yield losses with and without chemical treatments. Our validation with real data shows that AgGym can be customized with limited data to simulate yield outcomes under various biotic stress conditions. We further demonstrate that deep reinforcement learning (RL) policies can be trained using AgGym for designing ultra-precise biotic stress mitigation strategies with potential to increase yield recovery with less chemicals and lower cost. Our proposed framework enables personalized decision support that can transform biotic stress management from being schedule based and reactive to opportunistic and prescriptive. We also release the AgGym software implementation as a community resource and invite experts to contribute to this open-sourced publicly available modular environment framework. The source code can be accessed at: https://github.com/SCSLabISU/AgGym.
As an indispensable process in the microencapsulation of active substances, emulsion preparation has a significant impact on microencapsulated products. In this study, five primary emulsions of paprika oleoresin (PO, the natural colourant extracted from the fruit peel of Capsicum annuum L.) with different particle sizes (255–901.7 nm) were prepared using three industrialized pulverization-inducing techniques (stirring, ultrasound induction, and high-pressure homogenization). Subsequently, the PO emulsion was microencapsulated via spray drying. The effects of the different induction methods on the physicochemical properties, digestive behaviour, antioxidant activity, and storage stability of PO microencapsulated powder were investigated. The results showed that ultrasound and high-pressure homogenization induction could improve the encapsulation efficiency, solubility, and rehydration capacity of the microcapsules. In vitro digestion studies showed that ultrasound and high-pressure homogenization induction significantly increased the apparent solubility and dissolution of the microcapsules. High-pressure homogenization induction significantly improved the antioxidant capacity of the microcapsules, while high-intensity ultrasound (600 W) induction slowed down the degradation of the microcapsule fats and oils under short-term UV and long-term natural light exposure. Our study showed that ultrasound and high-pressure homogenization equipment could successfully be used to prepare emulsions containing nanoscale capsicum oil resin particles, improve their functional properties, and enhance the oral bioavailability of this bioactive product.
Water shortage continues to threaten the productivity of rapeseed in China dry-land planting system of china. There is an urgent need to build up efficient water saving management practices. Therefore, the field experiment was conducted by using a randomized complete black design with three replications under two cultivation practices: RF: ridge-furrow rainwater collection system, and CP: conventional flat planting; with four different mulching materials, such as plastic film mulching (PM); biodegradable film mulching (BM); straw mulch (SM) and no mulch (NM) were used in this study. We found that under different mulching materials, cultivation practices have a considerable effect on rainwater collection and improvement of soil water storage. Under the RF-PM and RF-BM treatments can considerably improve rapeseed photosynthesis (Pn, 54.1%), ETR (50.9%), ΦpsII (38.4%), the maximum quantum efficiency (Fv/Fm, 8.9%), Fv/Fo (25.7%) and Fv/Fm′ (26.1%), at the bolting, flowering and seed filling stage. These enhancements were attributed to the significant increase in soil water storage, total chlorophyll ab (59.4%), and chlorophyll stability index, as well as the decrease in evapotranspiration (ET, 3.9%), all of which improved water use efficiency (WUE, 28.0%), cuticular wax composition, grain yield (25.2%) and economic return (10459 Yuan ha−1) of rapeseed. These results showed that the RF planting practice using PM mulching materials is the best water-saving management practice to improve rapeseed photosynthesis, fluorescence, cuticular wax composition, WUE, and productivity in dry-land agricultural systems.
Fruit maturity grading is the key factor for fruit export where maturity consistence and standard are required. This paper proposes a non-destructive approach for pineapple maturity grading and pineapple localization based on object segmentation framework which has enhanced for training a robust model with small dataset. We introduced a multi-object sampling technique in augmentation process to generate images from a small dataset taken under controlled conditions to generalize the model for a more practical dataset. We identify the robustness of object segmentation models, Mask R-CNN over other models, e.g., Faster R-CNN, RetinaNet and CenterMask through mean average precision (mAP), detection ratio to explore the false positives detected, precision-recall curve and computational time. The optimal threshold selection which is crucial especially for sensitive small dataset to achieve high detection performance is proposed in this work using mAP and detection ratio. Our proposed framework enhances the model generalization and achieves mAP of 86.7%, AP50 and AP75 at 97.98% and APunripe, APpartially_ripe and APfully_ripe of 99.20%, 96.58% and 98.63%, respectively. Additional insights of the models developed with our small dataset are explained along with the experimental results which are suggested for future.
Industrial discharge of heavy metals severely deteriorates surface water quality in many parts of the world, particularly in lower-middle-income countries like Bangladesh. This study collected published data from 30 different surface water bodies in Bangladesh, including rivers, lakes, freshwater wetlands (Haors), and river estuaries, on mean concentrations of 12 heavy metals (Cd, Pb, Cr, Hg, Zn, Cu, Ni, Al, Fe, Mn, As, and Co) in surface water bodies from 2010 to 2022. The study aimed to explore the pollution source and levels of heavy metals in the surface water of Bangladesh. The water quality status and correlations between variables were assessed using the heavy metal pollution index (HPI), heavy metal evaluation index (HEI), and principal component analysis (PCA). The analysis results showed that the average heavy metal concentrations in the surface water of Bangladesh were in the order of Fe>Al>Mn>Cr>Zn>Cu>As>Ni>Pb>Co>Cd>Hg in the range of 3.98 ppm to 0.004 ppm. It also showed that Dhaka, Chittagong, Mymensingh divisions, and Bogra city of Rajshahi division are the most polluted areas of Bangladesh in terms of heavy metal concentration, whereas Khulna and Sylhet divisions are moderately polluted. The results showed that about 83.3 % of water bodies have HPI values greater than 100, which is considered unsafe for consumption. However, the HEI analysis revealed that about 46.7 % of water bodies were in the high pollution category (HEI > 20). The correlation matrix of heavy metals illustrated strong positive linear relationships between Cr and Co, Cu and As, Cu and Cd, and As and Cd. The principal component analysis suggested that the most contributing sources of pollution in the studied area are related to different anthropogenic activities, such as municipal waste and industrial effluent discharge, including tanneries, textile and dyeing industries, shipbreaking yards, and gas production plants, as well as agricultural runoff.
Abstract Artificial intelligence (AI) can be used in a variety of fields and has the potential to alter how we currently view farming. Due to its emphasis on effectiveness and usability artificial intelligence has the largest impact on agriculture of all industries. We highlight the automation-supporting technologies such as Artificial Intelligence (AI), Machine Learning, and Long-Range (LoRa) technology which provides data integrity and protection. We also offer a structure for smart farming that depends on the location of data processing after a comprehensive investigation of numerous designs. As part of our future study we have divided the unresolved difficulties in smart agriculture into two categories such as networking issues and technology issues. Artificial Intelligence and Machine Learning are examples of technologies whereas the Moderate Resolution Imaging Spectroradiometer satellite and LoRa are used for all network-related jobs. The goal of the research is to deploy a network of sensors throughout agricultural fields to gather real-time information on a variety of environmental factors including temperature, humidity, soil moisture and nutrient levels. The seamless data transmission and communication made possible by these sensors’ integration with Internet of Things technologies. With the use of AI techniques and algorithms the gathered data is examined. The technology may offer practical insights and suggestions for improving agricultural practices because the AI models are trained to spot patterns, correlations, and anomalies in the data. We are also focusing on indoor farming by supplying Ultra Violet radiation and artificial lighting in accordance with plant growth. When a pest assault is detected using AI and LoRa even in poor or no network coverage area and notifies the farmer’s mobile in any part of the world. The irrigation system is put to the test with various plants at various humidity and temperature levels in both dry and typical situations. To keep the water content in those specific regions soil moisture sensors are used.